μLayer: Low Latency On-Device Inference Using Cooperative Single-Layer Acceleration and Processor-Friendly Quantization.
Youngsok KimJoonsung KimDongju ChaeDaehyun KimJangwoo KimPublished in: EuroSys (2019)
Keyphrases
- single layer
- low latency
- high speed
- multi layer
- multiple layers
- neural network
- neural nets
- high bandwidth
- high throughput
- data acquisition
- virtual machine
- inter layer
- highly efficient
- hopfield neural network
- scalable video coding
- feed forward neural networks
- stream processing
- real time
- hidden layer
- video sequences
- microarray
- machine learning
- multithreading
- base layer
- computational complexity